模組:Jptools
 | 呢個模組已經被評為alpha版，可以接受第三方輸入，並可以用喺少量版以檢查有冇問題，但需要受到見識。歡迎提供新功能或者修改佢輸入輸出機制嘅建議。 |
概要 編輯
{{#invoke:jptools | yalify | 參數... }}
{{#invoke:jptools | ruby | 參數... }}
用途 編輯
睇埋 編輯
校對表 編輯
耶魯粵語拼音 編輯
Chēun Híu, Maahng Houh Yìhn
Chēun mìhn bāt gok híu,
Chyu chyu màhn tàih níuh.
Yeh lòih fūng yúh sīng,
Fā lohk jī dō síu.
劉錫祥拼音 編輯
Chun1° Hiu2, Maang6 Ho6 Yin4
Chun1° min4 bat1° gok3 hiu2,
Chue3 chue3 man4 tai4 niu5.
Ye6 loi4 fung1° yue5 sing1°,
Fa1° lok6 ji1° doh1° siu2.
教育學院拼音方案 編輯
Tsoen1 Hiu2, Maang6 Hou6 Jin4
Tsoen1 min4 bat7 gok8 hiu2,
Tsy3 tsy3 man4 tai4 niu5.
Je6 loi4 fung1 jy5 sing1,
Faa1 lok9 dzi1 do1 siu2.
粵語注音符號 編輯
1932 編輯
ㄧ
ㄨ˘ ㄧㄊ˙ ㄨㄣˊ ㄅㄎ˙ ㄈㄨㄥ ㄊㄨㄥˊ ㄧㄊʻ ㄊㄨˇ ㄏㄧˇ 
ㄩˋ 
ㄤ ㄌ
ㄣˆ ㄅㄧㄣ ㄍㄛˋ ㄍㄝˋ ㄅㄨㄣˇ ㄧˆ ㄉㄞˆ.
ㄧㄊ˙ ㄣˆ ㄊㄧˇ ㄍㄧㄣˋ ㄧㄊ˙ ㄍㄛˋ ㄏㄤˊ ㄌㄡˆ ㄍㄝˋ ㄧㄣˊ ㄣ ㄥˆ ㄎ ㄩˆ ㄧㄊ˙ ㄍㄧㄣˆ 
ㄥˊ ㄇㄧㄣˊ ㄆㄡˊ.
ㄎㄧ˘ ㄉㄟˆ ㄌㄥ˘ ㄍㄛˋ ㄧㄣˊ ㄨˆ ㄨㄚˆ,
ㄫㄛ˘ ㄉㄟˆ ㄊㄧˇ ㄅㄧㄣ ㄍㄛˋ ㄋㄥˊ ㄍㄨˋ ㄧㄣ ㄧˇ ㄋㄧ ㄍㄛˋ ㄏㄤˊ ㄌㄡˆ ㄍㄝˋ ㄧㄣˊ ㄥ ㄎㄧ˘ ㄍㄝˋ ㄥˊ ㄆㄡˊ ㄊㄩㄊ ㄌㄛㄎʻ ㄌㄧˊ ㄚ,
ㄨˆ ㄩㄣˋ ㄅㄧㄣ ㄍㄛˋ ㄍㄝˋ ㄅㄨㄣˇ ㄧˆ ㄉㄞˆ.
1950 編輯
ㄧㄡ ㄧ̣ ㄨㄣ ㄅ̣ ㄈㄨ̣ ㄊㄨ̣ ㄧ̣ ㄊㄡ ㄏㄟ ㄒㄩ ㄐㄤ ㄌ
̣ ㄅㄧ̣ ㄍㄛ ㄍㄝ ㄅㄨ̣ ㄒㄧ ㄉㄞ.
ㄧ̣ ㄐㄣ ㄊㄟ ㄍㄧ̣ ㄧ̣ ㄍㄛ ㄏㄤ ㄌㄛㄨ ㄍㄝ ㄧㄣ ㄒㄣ ㄒ̣ ㄐ̣ ㄐㄩ ㄧ̣ ㄍㄧ̣ ㄑ̣ ㄇㄧ̣ ㄆㄛㄨ.
ㄎㄧ ㄉㄝㄧ ㄌ̣ ㄍㄛ ㄧㄣ ㄐㄡ ㄨㄚ,
ㄫㄛ ㄉㄝㄧ ㄊㄟ ㄅㄧ̣ ㄍㄛ ㄋㄥ ㄍㄡ ㄒㄧ̣ ㄒㄟ ㄋㄧ ㄍㄛ ㄏㄤ ㄌㄛㄨ ㄍㄝ ㄧㄣ ㄐ̣ ㄎㄧ ㄍㄝ ㄑ̣ ㄆㄛㄨ ㄊㄩ̣ ㄌㄛ̣ ㄌㄟ ㄚ,
ㄐㄡ ㄒㄩ̣ ㄅㄧ̣ ㄍㄛ ㄍㄝ ㄅㄨ̣ ㄒㄧ ㄉㄞ.
| 上面嘅解係穿透包含咗自模組:Jptools/doc。 (改 | 史) 編者可以響呢個模組嘅沙盤 (開 | 鏡)同埋試例 (開)版度試驗佢。 呢個模組嘅細版。 |
-- vim: set sw=4 ts=4 ai sm :
---- 呢個係少眾注音模組，原版係2021年做 project 嗰陣做耶魯注音用，同粵維無關。
---- 粵維 Lua 版 2023 年由 Perl 譯咗之後，後來加入其他耶魯以外嘅其他方案。
----
---- 原程式唔會好小心咁解析粵拼，只係求其解析（用最少心機做到 project 就算，原碼只係做校對用嘅架生仔），
---- 所以模組解析粵拼都好求其，如果輸入唔係粵拼，輸出係 ｢未定義｣⸺即係可能係亂碼、垃圾、錯嘢等等
require ('strict');
local p = {};
local use_dotted_i_p = false;
local use_macrons_p = true;
local styles = '模組:jptools/styles.css';
local dot = mw.ustring.char(0x323);
if true then
local z = require('模組:書名');
p.cvs = z.cvs;
end
local function interpret_boolean( s )
return s:match('^%s*true%s*$')
or s:match('^%s*yes%s*$')
or s:match('^%s*0*1%s*$');
end
local function remove_tags( s )
local it;
if s then
it = s:gsub('<[^<>]*>', ''):gsub("'''", ''):gsub("''", '');
end
return it;
end
local function td_insert_attr( td, attr )
-- I hate Lua so much
if not td:match('|.*|') then
td = '|' .. attr .. td;
else
td = td:gsub('|', '|' .. attr .. ' ', 1);
end
return td;
end
local jyutping_blacklist = { 'sh', 'sj' };
local mappings;
local tone_mappings = {
['braille'] = {
['novenary'] = {
['suffix'] = { '', '⠁', '⠈', '⠄', '⠠', '⠂', '', '⠐', '⠄' };
};
};
['hangul'] = {
['senary'] = {
-- FIXME: can't understand the description, doing own thing based on description in PowerPoint
-- PowerPoint says originally, ˊsœŋ was represented by 2 dots (on left of hangul), ˉhœy by 1 dot
-- need way to distinguish between 2,3 and 5,6 so 2,3 will go below and 4,5,6 will go below
['prefix'] = {
'<span class=yue-hang-tone-1>',
'<span class=yue-hang-tone-2>',
'<span class=yue-hang-tone-3>',
'<span class=yue-hang-tone-4>',
'<span class=yue-hang-tone-5>',
'<span class=yue-hang-tone-6>',
};
['suffix'] = { '</span>', '</span>', '</span>', '</span>', '</span>', '</span>', };
};
};
['ipa_phonemic'] = {
['senary'] = {
['prefix'] = { 'ˈ', 'ˊ', 'ˉ', 'ˌ', 'ˏ', 'ˍ' };
};
};
['ipa_phonetic'] = {
['senary'] = {
['suffix'] = { '˥', '˧˥', '˧', '˩', '˨˧', '˨' };
};
};
['jyutping'] = {
['senary'] = {
['suffix'] = { '1', '2', '3', '4', '5', '6' };
};
};
['pinyin_1960'] = {
['senary'] = {
['suffix'] = { '1', '2', '3', '4', '5', '6' };
};
};
['pinyin_1980'] = {
['senary'] = {
['suffix'] = { '1', '2', '3', '4', '5', '6' };
};
};
['zhuyin_1931'] = {
['novenary'] = {
['suffix'] = { '', 'ˇ', 'ˋ', 'ˊ', '˘', 'ˆ', '˙', '', 'ʻ' };
};
};
['zhuyin_1932'] = {
['novenary'] = {
['suffix'] = { '', 'ˇ', 'ˋ', 'ˊ', '˘', 'ˆ', '˙', '', 'ʻ' };
};
};
['zhuyin_1950'] = {
['novenary'] = {
['suffix'] = { '', '', '', '', '', '', '', '', '' }; -- not a mistake - tones are absolutely not marked
};
};
};
tone_mappings.hangul_tswong = tone_mappings.hangul;
tone_mappings.hangul_sykim = tone_mappings.hangul;
local schemes = {
['點字'] = 'braille';
['凸字'] = 'braille';
['盲文'] = 'braille';
['諺文'] = 'hangul';
['教院'] = 'hkie';
['國際'] = 'ipa';
['萬國'] = 'ipa';
['粵拼'] = 'jyutping';
['廣拼'] = 'pinyin';
['耶魯'] = 'yale';
['注音'] = 'zhuyin';
['黃錫凌'] = 'ipa_phonemic';
['劉錫祥'] = 'sidneylau';
['黃錫凌式'] = 'ipa_phonemic';
['國際音標'] = 'ipa';
['萬國音標'] = 'ipa';
['粵語諺文'] = 'hangul';
['教育學院'] = 'hkie';
['廣州拼音'] = 'pinyin';
['注音符號'] = 'zhuyin';
['粵語注音'] = 'zhuyin';
['廣州話拼音'] = 'pinyin';
['粵語注音符號'] = 'zhuyin';
['教育學院拼音方案'] = 'hkie';
['bopomofo'] = 'zhuyin';
['bpmf'] = 'zhuyin';
['braille'] = 'braille';
['hangeul'] = 'hangul';
['hangul'] = 'hangul';
['hkie'] = 'hkie';
['ipa'] = 'ipa';
['jyutping'] = 'jyutping';
['lau'] = 'sidneylau';
['pinyin'] = 'pinyin';
['sidneylau'] = 'sidneylau';
['yale'] = 'yale';
['zhuyin'] = 'zhuyin';
};
local variants = {
['hangul'] = {
['金昔研'] = 'sykim';
['黃得森'] = 'tswong';
['sykim'] = 'sykim';
['tswong'] = 'tswong';
};
['ipa'] = {
['寛式'] = 'phonemic';
['寬式'] = 'phonemic';
['嚴式'] = 'phonetic';
['黃錫凌'] = 'phonemic';
['黃錫凌式'] = 'phonemic';
['phonemic'] = 'phonemic';
['phonetic'] = 'phonetic';
};
['pinyin'] = {
['1960'] = '1960';
['1980'] = '1980';
};
['zhuyin'] = {
['民國'] = '1932';
['中共'] = '1950';
['人民'] = '1950';
['趙雅庭'] = '1931';
['1931'] = '1931';
['1932'] = '1932';
['1950'] = '1950';
['1952'] = '1950'; -- source: [[廣州話拼音方案]]
};
};
local default_scheme = 'jyutping';
local fallback_scheme = 'ipa';
local default_variants = {
['hangul'] = 'tswong';
['ipa'] = 'phonemic';
['pinyin'] = '1980';
['zhuyin'] = '1950';
};
local C1 = {
[''] = mw.ustring.char(0x110b);
['ʾ'] = mw.ustring.char(0x1159);
['bb'] = mw.ustring.char(0x1108);
['f'] = mw.ustring.char(0x1157); -- per [[:en:Hangul]], f is 112b or 1157, but not composable so unusable
['ng'] = mw.ustring.char(0x114c);
['w'] = mw.ustring.char(0x111d); -- per [[:en:Hangul]]
['y'] = mw.ustring.char(0x1147); -- per [[:en:Hangul]]
};
local C2 = {
['l'] = mw.ustring.char(0x11af); -- think of ł = /w/
['m'] = mw.ustring.char(0x11b7);
['n'] = mw.ustring.char(0x11ab);
['ng'] = mw.ustring.char(0x11bc);
['b'] = mw.ustring.char(0x11bb);
['d'] = mw.ustring.char(0x11ae);
['g'] = mw.ustring.char(0x11a8); -- think of Ger g > Eng y... I'm out of ideas
['p'] = mw.ustring.char(0x11c1);
['t'] = mw.ustring.char(0x11c0);
['k'] = mw.ustring.char(0x11bf);
['h'] = mw.ustring.char(0x11c2);
['j'] = mw.ustring.char(0x11bd);
['z'] = mw.ustring.char(0x11eb);
['lb'] = mw.ustring.char(0x11b2);
['lg'] = mw.ustring.char(0x11b0);
['lh'] = mw.ustring.char(0x11b6);
['ll'] = mw.ustring.char(0x11d0);
['lm'] = mw.ustring.char(0x11b1);
['ln'] = mw.ustring.char(0x11cd);
['lp'] = mw.ustring.char(0x11b5);
['lt'] = mw.ustring.char(0x11b4);
['nc'] = mw.ustring.char(0xd7cc);
['ngs'] = mw.ustring.char(0x11f1);
['nj'] = mw.ustring.char(0x11ac);
['ns'] = mw.ustring.char(0x11c7);
['s'] = mw.ustring.char(0x11ba);
['sk'] = mw.ustring.char(0x11e7);
['sm'] = mw.ustring.char(0xd7ea);
['sp'] = mw.ustring.char(0x11ea);
['st'] = mw.ustring.char(0x11e8);
};
local V = {
['aa'] = mw.ustring.char(0x1161);
['aai'] = mw.ustring.char(0x1162);
['ə'] = mw.ustring.char(0x119e);
['ae'] = mw.ustring.char(0x1162); -- per [[:en:Hangul]], this is /ɛ/
['e'] = mw.ustring.char(0x1166);
['əi'] = mw.ustring.char(0x11a1);
['ei'] = mw.ustring.char(0x1164); -- per [[:en:Hangul]], this is /e/
['eo'] = mw.ustring.char(0x1165);
['eo_u'] = mw.ustring.char(0x117b);
['eu'] = mw.ustring.char(0x1173);
['i'] = mw.ustring.char(0x1175);
['o'] = mw.ustring.char(0x1169);
['oi'] = mw.ustring.char(0x116c); -- called oe; per [[:en:Hangul]], this should be /œ/, which doesn't work
['u'] = mw.ustring.char(0x116e);
['waa'] = mw.ustring.char(0x116a);
['waai'] = mw.ustring.char(0x118A);
['wai'] = '(WAI)';
['wa'] = mw.ustring.char(0x118A);
['wae'] = mw.ustring.char(0x116b); -- per [[:en:Hangul]], this is /wɛ/
['we'] = mw.ustring.char(0x1170); -- per [[:en:Hangul]], this is /we/
['weo'] = mw.ustring.char(0x116f);
['weu'] = '(WEU)';
['wi'] = mw.ustring.char(0x1171); -- this is ui; per [[:en:Hangul]], this should be /y/, which doesn't work
['wo'] = mw.ustring.char(0x1182); -- XXX o + o
['woi'] = mw.ustring.char(0xd7b1); -- XXX o + o + i
['wu'] = mw.ustring.char(0x118d);
['wyu'] = '(WYU)';
['yaa'] = mw.ustring.char(0x1163);
['yaai'] = mw.ustring.char(0x1164);
['yə'] = mw.ustring.char(0x119d);
['yae'] = mw.ustring.char(0x1164); -- per [[:en:Hangul]], this is /jɛ/
['yeo'] = mw.ustring.char(0x1167);
['yeo_u'] = mw.ustring.char(0x117e);
['yo'] = mw.ustring.char(0x116d);
['yoi'] = mw.ustring.char(0x1188);
['ye'] = mw.ustring.char(0x1168); -- per [[:en:Hangul]], this is /je/
['yeu'] = mw.ustring.char(0x119c);
['yi'] = mw.ustring.char(0x1174);
['y_i'] = mw.ustring.char(0xd7c4);
['yu'] = mw.ustring.char(0x1172);
};
local function reconstruct_yale (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
local it = '';
if initial_consonant == nil then -- I hate Lua
initial_consonant = '';
end
if root == nil then -- I hate Lua
root = '';
end
if punctuation == nil then -- I hate Lua
punctuation = '';
end
local initial_vowel, other_vowels, final = mw.ustring.match(root, '^(ng)([aeiou]*)(.*)');
if not final then
initial_vowel, other_vowels, final = mw.ustring.match(root, '^(yu)([aeiou]*)(.*)');
if not final then
initial_vowel, other_vowels, final = mw.ustring.match(root, '^(%a)([aeiou]*)(.*)');
end
end
if initial_vowel == nil then -- I hate Lua
initial_vowel = '';
end
if other_vowels == nil then -- I hate Lua
other_vowels = '';
end
if final == nil then -- I hate Lua
final = '';
end
local mod1, mod2;
if tone then
if tone.actual.senary == 1 and use_macrons_p then
mod1 = '\204\132'; -- U+0304
elseif tone.actual.quaternary == 2 then
mod1 = '\204\129'; -- U+0301
elseif tone.actual.quaternary == 1 then
mod1 = '\204\128'; -- U+0300
else
mod1 = '';
end
if tone.actual.masculine_p then
mod2 = 'h';
else
mod2 = '';
end
end
if use_dotted_i_p and (not tone or tone.actual.quaternary == 3) and all_caps_p then
initial_vowel = mw.ustring.gsub(initial_vowel, 'i', 'i̇'); -- append U+0307 I hate Lua
end
if not (initial_consonant == 'y' and initial_vowel:sub(1, 1) == 'y') then
it = it .. initial_consonant;
end
-- XXX yu is irregular in that any diacritic is placed above the u, not the y
-- XXX this is not explained in the article but can be deduced from the sample poem
-- XXX and can be confirmed by searching inside the referenced book
local part1, part2 = mw.ustring.match(initial_vowel, '^(y%a)(%a*)$');
if part1 then
it = it .. part1 .. mod1 .. part2 .. other_vowels .. mod2 .. final .. punctuation;
else
part1, part2 = mw.ustring.match(initial_vowel, '^(%a)(%a*)$');
if part1 then
it = it .. part1 .. mod1 .. part2 .. other_vowels .. mod2 .. final .. punctuation;
end
end
if capped_p then
it = mw.ustring.upper(mw.ustring.sub(it, 1, 1)) .. mw.ustring.sub(it, 2);
elseif all_caps_p then
it = mw.ustring.upper(it);
end
return it;
end
local function reconstruct_sidneylau (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
local it = '';
if initial_consonant then
it = it .. initial_consonant;
end
if root then
it = it .. root;
end
if tone then
it = it .. '<sup class="yue-latn-tone">';
if tone.actual.senary == 1 and not tone.canonical then
-- XXX We are screwed. Sydney Lau tone 1° is Jyutping 1
-- XXX and Sydney Lau tone 1 is a “falling” tone that is “very rare”.
-- XXX Jyutping doesn't distinguish between the two so.
it = it .. '1°'; -- XXX assumption here
elseif tone.canonical and tone.canonical.senary ~= tone.actual.senary and tone.actual.senary == 1 then
it = it .. tone.canonical.senary .. '°';
elseif tone.canonical and tone.canonical.senary ~= tone.actual.senary and tone.actual.senary == 2 then
it = it .. tone.canonical.senary .. '*';
else
it = it .. tone.actual.senary;
end
it = it .. '</sup>';
end
if punctuation then
it = it .. punctuation;
end
if capped_p then
it = mw.ustring.upper(mw.ustring.sub(it, 1, 1)) .. mw.ustring.sub(it, 2);
elseif all_caps_p then
it = mw.ustring.upper(it);
end
return it;
end
local function reconstruct_jyutping (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
local it = '';
if initial_consonant then
it = it .. initial_consonant;
end
if root then
it = it .. root;
end
if tone then
it = it .. '<span class="jpingtone">'; -- mimic jpingauto
if tone.canonical and tone.canonical.senary ~= tone.actual.senary then
it = it .. tone.canonical.senary .. '*';
end
it = it .. tone.actual.senary .. '</span>';
end
if punctuation then
it = it .. punctuation;
end
if capped_p then
it = mw.ustring.upper(mw.ustring.sub(it, 1, 1)) .. mw.ustring.sub(it, 2);
elseif all_caps_p then
it = mw.ustring.upper(it);
end
return it;
end
local function reconstruct_ipa (initial_consonant, root, tone, punctuation, id)
local it = '';
local mapping = mappings[id];
local tone_mapping = tone_mappings[id];
if tone and tone_mapping.senary
and tone_mapping.senary.prefix
and tone_mapping.senary.prefix[tone.actual.senary] then
it = it .. tone_mapping.senary.prefix[tone.actual.senary];
elseif tone
and tone_mapping.novenary
and tone_mapping.novenary.prefix
and tone_mapping.novenary.prefix[tone.actual.novenary] then
it = it .. tone_mapping.novenary.prefix[tone.actual.novenary];
end
if initial_consonant then
it = it .. initial_consonant;
end
if root then
it = it .. root;
end
if tone and tone_mapping.senary
and tone_mapping.senary.suffix
and tone_mapping.senary.suffix[tone.actual.senary] then
it = it .. tone_mapping.senary.suffix[tone.actual.senary];
elseif tone
and tone_mapping.novenary
and tone_mapping.novenary.suffix
and tone_mapping.novenary.suffix[tone.actual.novenary] then
it = it .. tone_mapping.novenary.suffix[tone.actual.novenary];
end
if punctuation and not mapping.ignore_punctuation_p then
it = it .. punctuation;
end
return it;
end
local function reconstruct_ipa_phonemic (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_ipa(initial_consonant, root, tone, punctuation, 'ipa_phonemic');
end
local function reconstruct_ipa_phonetic (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_ipa(initial_consonant, root, tone, punctuation, 'ipa_phonetic');
end
local function reconstruct_pinyin (initial_consonant, root, tone, punctuation, id)
local it = reconstruct_ipa(initial_consonant, root, tone, punctuation, id);
it = mw.ustring.gsub(it, 'z([iü])', 'j%1');
it = mw.ustring.gsub(it, 'c([iü])', 'q%1');
it = mw.ustring.gsub(it, 's([iü])', 'x%1');
it = mw.ustring.gsub(it, '([jqx])ü', '%1u');
return it;
end
local function reconstruct_pinyin_1960 (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_pinyin (initial_consonant, root, tone, punctuation, 'pinyin_1960');
end
local function reconstruct_pinyin_1980 (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_pinyin (initial_consonant, root, tone, punctuation, 'pinyin_1980');
end
local function reconstruct_hkie (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
local it = '';
if initial_consonant then
it = it .. initial_consonant;
end
if root then
it = it .. root;
end
if tone then
it = it .. '<sup class="yue-latn-tone">';
it = it .. tone.actual.novenary;
it = it .. '</sup>';
end
if punctuation then
it = it .. punctuation;
end
if capped_p then
it = mw.ustring.upper(mw.ustring.sub(it, 1, 1)) .. mw.ustring.sub(it, 2);
elseif all_caps_p then
it = mw.ustring.upper(it);
end
return it;
end
local function reconstruct_zhuyin (initial_consonant, root, tone, punctuation, id)
if initial_consonant == 'ㄧ' and mw.ustring.match(root, '^[ㄧㄩ]') then
initial_consonant = nil;
end
return reconstruct_ipa(initial_consonant, root, tone, punctuation, id);
end
local function reconstruct_zhuyin_1931 (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_zhuyin (initial_consonant, root, tone, punctuation, 'zhuyin_1931');
end
local function reconstruct_zhuyin_1932 (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_zhuyin (initial_consonant, root, tone, punctuation, 'zhuyin_1932');
end
local function reconstruct_zhuyin_1950 (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_zhuyin (initial_consonant, root, tone, punctuation, 'zhuyin_1950');
end
local function reconstruct_hangul (initial_consonant, root, tone, punctuation, id)
local onset, glide, s;
if type(initial_consonant) == 'table' then
onset = initial_consonant[1];
glide = initial_consonant[2];
else
onset = initial_consonant;
end
if type(root) == 'table' then
local i = glide;
if not i then
i = 1;
end
if root[i] then
if root[i][1] then
s = table.concat(root[i]);
else
error('Internal error: Unexpected value ' .. p.cvs(root[i]) .. ' for i=' .. p.cvs(i) .. ' (root=' .. p.cvs(root) .. ')');
end
else
s = 'ERROR(no root for i=' .. p.cvs(i) .. ')';
end
if onset and onset ~= '' then
s = onset .. s;
end
-- don't trust the tables. look at the first jamo and check that it's not a vowel.
-- if it's a vowel insert the zero consonant
local det = mw.ustring.codepoint(s);
if (det >= 0x1160 and det <= 0x11a7) or (det >= 0xd7b0 and det <= 0xd7ca) then
s = C1[''] . s;
end
-- check the last consonant too. if it's a starting consonant we screwed up somewhere.
det = mw.ustring.codepoint(mw.ustring.sub(s, -1, -1));
if (det >= 0x1100 and det <= 0x115f) or (det >= 0xa960 and det <= 0xa97f) then
error('Internal error: ' .. s .. ': Constructed hangul ends with starting consonant U+' .. string.format('%x', det));
end
elseif (onset
and onset ~= ''
and onset ~= mappings[id].initials['']
and onset ~= C1['']
and onset ~= C1['ʾ']) or glide then
error('Internal error: ' .. root .. ': Not expecting onset but onset=' .. p.cvs(onset) .. ', glide=' .. p.cvs(glide));
else
s = root;
end
return reconstruct_ipa(nil, s, tone, punctuation, id);
end
local function reconstruct_hangul_tswong (initial_consonant, root, tone, punctuation, id)
return reconstruct_hangul(initial_consonant, root, tone, punctuation, 'hangul_tswong');
end
local function reconstruct_braille (initial_consonant, root, tone, punctuation, id)
return reconstruct_ipa(initial_consonant, root, tone, punctuation, 'braille');
end
mappings = {
-- source: [[粵語諺文]]
-- any form of precomposing would not work, so we'll transform it into some kind of internal representation
-- then attempt to reconstruct the actual hangul in reconstruct_hangul_tswong
['hangul_tswong'] = {
['label'] = '諺文';
['link'] = '粵語諺文#黃得森方案';
['sublabel'] = '黃得森方案';
['f'] = reconstruct_hangul_tswong;
['ignore_spaces_p'] = true,
['initials'] = {
[''] = C1[''];
['b'] = 'ᄇ'; -- U+1107
['p'] = 'ᄑ'; -- U+1111
['m'] = 'ᄆ'; -- U+1106
['f'] = mw.ustring.char(0x1108);
['d'] = 'ᄃ'; -- U+1103
['t'] = 'ᄐ'; -- U+1110
['n'] = 'ᄂ'; -- U+1102
['l'] = 'ᄅ'; -- U+1105
['g'] = 'ᄀ'; -- U+1100
['k'] = 'ᄏ'; -- U+110F
['ng'] = C1[''];
['h'] = 'ᄒ'; -- U+1112
['gw'] = { 'ᄀ', 'W' }; -- U+1100
['kw'] = { 'ᄏ', 'W' }; -- U+110F
['w'] = { C1[''], 'W' }; -- U+110B
['z'] = 'ᄌ'; -- U+110C
['c'] = 'ᄎ'; -- U+110E
['s'] = 'ᄉ'; -- U+1109
['j'] = { C1[''], 'Y' }; -- U+110B
};
['finals'] = {
['aa'] = { { V.aa }; ['W'] = { V.waa }; ['Y'] = { V.yaa }; };
['aai'] = { { V.ae }; ['W'] = { V.wae }; ['Y'] = { V.yae }; };
['aau'] = { { V.eo }; ['W'] = { V.weo }; ['Y'] = { V.yeo }; };
['aam'] = { { V.aa, C2.m }; ['W'] = { V.waa, C2.m }; ['Y'] = { V.yaa, C2.m }; };
['aan'] = { { V.aa, C2.n }; ['W'] = { V.waa, C2.n }; ['Y'] = { V.yaa, C2.n }; };
['aang'] = { { V.aa, C2.ng }; ['W'] = { V.waa, C2.ng }; ['Y'] = { V.yaa, C2.ng }; };
['aap'] = { { V.aa, C2.b }; ['W'] = { V.waa, C2.b }; ['Y'] = { V.yaa, C2.b }; };
['aat'] = { { V.aa, C2.d }; ['W'] = { V.waa, C2.d }; ['Y'] = { V.yaa, C2.d }; };
['aak'] = { { V.aa, C2.g }; ['W'] = { V.waa, C2.g }; ['Y'] = { V.yaa, C2.g }; };
['ai'] = { { V.ae, C2.s }; ['W'] = { V.wae, C2.s }; ['Y'] = { V.yae, C2.s }; };
['au'] = { { V.aa, C2.s }; ['W'] = { V.waa, C2.s }; ['Y'] = { V.yaa, C2.s }; };
['am'] = { { V.aa, C2.lm }; ['W'] = { V.waa, C2.lm }; ['Y'] = { V.yaa, C2.lm }; };
['an'] = { { V.aa, C2.nj }; ['W'] = { V.waa, C2.nj }; ['Y'] = { V.yaa, C2.nj }; };
['ang'] = { { V.aa, C2.h }; ['W'] = { V.waa, C2.h }; ['Y'] = { V.yaa, C2.h }; };
['ap'] = { { V.aa, C2.p }; ['W'] = { V.waa, C2.p }; ['Y'] = { V.yaa, C2.p }; };
['at'] = { { V.aa, C2.t }; ['W'] = { V.waa, C2.t }; ['Y'] = { V.yaa, C2.t }; };
['ak'] = { { V.aa, C2.k }; ['W'] = { V.waa, C2.k }; ['Y'] = { V.yaa, C2.k }; };
['e'] = { { V.e }; ['W'] = { V.we }; ['Y'] = { V.ye }; };
['ei'] = { { V.e, C2.s }; ['W'] = { V.we, C2.s }; ['Y'] = { V.ye, C2.s }; };
['eu'] = { { V.yeo }; ['W'] = { C1.w, V.weo }; ['Y'] = { C1.y, V.yeo }; };
['em'] = { { V.e, C2.m }; ['W'] = { V.we, C2.m }; ['Y'] = { V.ye, C2.m }; };
['en'] = { { V.e, C2.n }; ['W'] = { V.we, C2.n }; ['Y'] = { V.ye, C2.n }; };
['eng'] = { { V.e, C2.ng }; ['W'] = { V.we, C2.ng }; ['Y'] = { V.ye, C2.ng }; };
['ep'] = { { V.e, C2.b }; ['W'] = { V.we, C2.b }; ['Y'] = { V.ye, C2.b }; };
['ek'] = { { V.e, C2.g }; ['W'] = { V.we, C2.g }; ['Y'] = { V.ye, C2.g }; };
['i'] = { { V.i }; ['W'] = { V.wi }; ['Y'] = { V.i }; };
['iu'] = { { V.yu }; ['W'] = { C1.w, V.yu }; ['Y'] = { C1.y, V.yu }; };
['im'] = { { V.i, C2.m }; ['W'] = { V.wi, C2.m }; ['Y'] = { V.i, C2.m }; };
['in'] = { { V.i, C2.n }; ['W'] = { V.wi, C2.n }; ['Y'] = { V.i, C2.n }; };
['ing'] = { { V.e, C2.h }; ['W'] = { V.we, C2.h }; ['Y'] = { V.e, C2.h }; };
['ip'] = { { V.i, C2.b }; ['W'] = { V.wi, C2.b }; ['Y'] = { V.i, C2.b }; };
['it'] = { { V.i, C2.d }; ['W'] = { V.wi, C2.d }; ['Y'] = { V.i, C2.d }; };
['ik'] = { { V.e, C2.k }; ['W'] = { V.we, C2.k }; ['Y'] = { V.ye, C2.k }; };
['o'] = { { V.o }; ['W'] = { V.wo }; ['Y'] = { V.yo }; };
['oi'] = { { V.oi }; ['W'] = { V.woi }; ['Y'] = { V.yoi }; };
['ou'] = { { V.o, C2.s }; ['W'] = { V.wo, C2.s }; ['Y'] = { V.yo, C2.s }; };
['on'] = { { V.o, C2.n }; ['W'] = { V.wo, C2.n }; ['Y'] = { V.yo, C2.n }; };
['ong'] = { { V.o, C2.ng }; ['W'] = { V.wo, C2.ng }; ['Y'] = { V.yo, C2.ng }; };
['op'] = { { V.o, C2.b }; ['W'] = { V.wo, C2.b }; ['Y'] = { V.yo, C2.b }; };
['ot'] = { { V.o, C2.d }; ['W'] = { V.wo, C2.d }; ['Y'] = { V.yo, C2.d }; };
['ok'] = { { V.o, C2.k }; ['W'] = { V.wo, C2.k }; ['Y'] = { V.yo, C2.k }; };
['u'] = { { V.u }; ['W'] = { V.wu }; ['Y'] = { C1.y, V.u }; };
['ui'] = { { V.wi }; ['W'] = { V.wi }; ['Y'] = { C1.y, V.wi }; };
['un'] = { { V.u, C2.n }; ['W'] = { V.wu, C2.n }; ['Y'] = { C1.y, V.u, C2.n }; };
['ung'] = { { V.o, C2.h }; ['W'] = { V.wo, C2.h }; ['Y'] = { V.yo, C2.h }; };
['up'] = { { V.u, C2.b }; ['W'] = { V.wu, C2.b }; ['Y'] = { C1.y, V.u, C2.b }; };
['ut'] = { { V.u, C2.d }; ['W'] = { V.wu, C2.d }; ['Y'] = { C1.y, V.u, C2.d }; };
['uk'] = { { V.u, C2.g }; ['W'] = { V.wu, C2.g }; ['Y'] = { C1.y, V.u, C2.g }; };
['oe'] = { { V.eu }; ['W'] = { V.weu }; ['Y'] = { V.yoi }; };
['eoi'] = { { V.eu, C2.s }; ['W'] = { V.oi, C2.s }; ['Y'] = { V.yeu, C2.s }; };
['eon'] = { { V.eu, C2.nj }; ['W'] = { V.wo, C2.nj }; ['Y'] = { V.yo, C2.nj }; };
['oeng'] = { { V.eu, C2.ng }; ['W'] = { V.weu, C2.ng }; ['Y'] = { V.yo, C2.ng }; };
['eot'] = { { V.eu, C2.t }; ['W'] = { V.wo, C2.t }; ['Y'] = { V.yeu, C2.t }; };
['oet'] = { { V.eu, C2.d }; ['W'] = { V.wo, C2.d }; ['Y'] = { V.yeu, C2.d }; };
['oek'] = { { V.eu, C2.g }; ['W'] = { V.wo, C2.g }; ['Y'] = { V.yeu, C2.g }; };
['yu'] = { { V.yi }; ['W'] = { C1.w, V.yi }; ['Y'] = { V.yi }; };
['yun'] = { { V.yi, C2.n }; ['W'] = { C1.w, V.yi, C2.n }; ['Y'] = { V.yi, C2.n }; };
['yut'] = { { V.yi, C2.d }; ['W'] = { C1.w, V.yi, C2.d }; ['Y'] = { V.yi, C2.d }; };
['m'] = 'ㅁ';
['ng'] = 'ㅇ'; -- or ㄲ
};
};
['ipa_phonemic'] = {
['label'] = 'IPA';
['link'] = '黃錫凌式音標';
['prefix'] = '<span class=IPA>';
['suffix'] = '</span>';
['f'] = reconstruct_ipa_phonemic;
['initials'] = {
[''] = '';
['b'] = 'b';
['p'] = 'p';
['m'] = 'm';
['f'] = 'f';
['d'] = 'd';
['t'] = 't';
['n'] = 'n';
['l'] = 'l';
['g'] = 'ɡ';
['k'] = 'k';
['ng'] = 'ŋ';
['h'] = 'h';
['gw'] = 'ɡw';
['kw'] = 'kw';
['w'] = 'w';
['z'] = 'dz';
['c'] = 'ts';
['s'] = 's';
['sh'] = 'ʃ'; -- non-standard notation added to handle actual speech
['sj'] = 'ʃ'; -- non-standard notation added to handle actual speech
['j'] = 'j';
};
['finals'] = {
['aa'] = 'a';
['aai'] = 'ai';
['aau'] = 'au';
['aam'] = 'am';
['aan'] = 'an';
['aang'] = 'aŋ';
['aap'] = 'ap';
['aat'] = 'at';
['aak'] = 'ak';
['ai'] = 'ɐi';
['au'] = 'ɐu';
['am'] = 'ɐm';
['an'] = 'ɐn';
['ang'] = 'ɐŋ';
['ap'] = 'ɐp';
['at'] = 'ɐt';
['ak'] = 'ɐk';
['e'] = 'ɛ';
['ei'] = 'ei';
['eng'] = 'ɛŋ';
['ep'] = 'ɛp';
['et'] = 'ɛt';
['ek'] = 'ɛk';
['i'] = 'i';
['iu'] = 'iu';
['im'] = 'im';
['in'] = 'in';
['ing'] = 'iŋ';
['ip'] = 'ip';
['it'] = 'it';
['ik'] = 'ik';
['o'] = 'ɔ';
['oi'] = 'ɔi';
['ou'] = 'ou';
['on'] = 'ɔn';
['ong'] = 'ɔŋ';
['ot'] = 'ɔt';
['ok'] = 'ɔk';
['u'] = 'u';
['ui'] = 'ui';
['un'] = 'un';
['ung'] = 'uŋ';
['ut'] = 'ut';
['uk'] = 'uk';
['oe'] = 'œ';
['eoi'] = 'œy';
['eon'] = 'œn';
['oeng'] = 'œŋ';
['eot'] = 'œt'; -- FIXME non-standard, clash
['oet'] = 'œt';
['oek'] = 'œk';
['yu'] = 'y';
['yun'] = 'yn';
['yut'] = 'yt';
['m'] = 'm';
['ng'] = 'ŋ';
};
};
-- source: [[粵語注音符號]], with modifications
['ipa_phonetic'] = {
['label'] = 'IPA';
['link'] = '國際音標';
['sublabel'] = '嚴式';
['prefix'] = '<span class=IPA>[ '; -- U+200A hair space
['suffix'] = ' ]</span>'; -- ditto
['f'] = reconstruct_ipa_phonetic;
['ignore_punctuation_p'] = true,
['initials'] = {
[''] = 'ˀ';
['b'] = 'p';
['p'] = 'pʰ';
['m'] = 'm';
['f'] = 'f';
['d'] = 't';
['t'] = 'tʰ';
['n'] = 'n';
['l'] = 'l';
['g'] = 'k';
['k'] = 'kʰ';
['ng'] = 'ŋ';
['h'] = 'h';
['gw'] = 'kʷ';
['kw'] = 'kʷʰ';
['w'] = 'w';
['z'] = 't͡s';
['c'] = 't͡sʰ';
['s'] = 's';
['sh'] = 'ʃ'; -- non-standard notation added to handle actual speech
['sj'] = 'ʃ'; -- non-standard notation added to handle actual speech
['j'] = 'j';
};
['finals'] = {
['aa'] = 'a';
['aai'] = 'a:i';
['aau'] = 'a:u';
['aam'] = 'a:m';
['aan'] = 'a:n';
['aang'] = 'a:ŋ';
['aap'] = 'a:p̚';
['aat'] = 'a:t̚';
['aak'] = 'a:k̚';
['ai'] = 'ɐi';
['au'] = 'ɐu';
['am'] = 'ɐm';
['an'] = 'ɐn';
['ang'] = 'ɐŋ';
['ap'] = 'ɐp̚';
['at'] = 'ɐt̚';
['ak'] = 'ɐk̚';
['e'] = 'ɛ:';
['ei'] = 'ei';
['eng'] = 'ɛ:ŋ';
['ep'] = 'ɛp';
['et'] = 'ɛt';
['ek'] = 'ɛk̚';
['i'] = 'i:';
['iu'] = 'i:u';
['im'] = 'i:m';
['in'] = 'i:n';
['ing'] = 'ɪŋ';
['ip'] = 'i:p̚';
['it'] = 'i:t̚';
['ik'] = 'ɪk̚';
['o'] = 'ɔ';
['oi'] = 'ɔi';
['ou'] = 'ou';
['on'] = 'ɔn';
['ong'] = 'ɔŋ';
['ot'] = 'ɔt̚';
['ok'] = 'ɔk̚';
['u'] = 'u';
['ui'] = 'ui';
['un'] = 'un';
['ung'] = 'uŋ';
['ut'] = 'ut̚';
['uk'] = 'uk̚';
['oe'] = 'œ:';
['eoi'] = 'ɵy';
['eon'] = 'ɵn';
['oeng'] = 'œ:ŋ';
['eot'] = 'ɵt̚';
['oet'] = 'œt̚';
['oek'] = 'œ:k̚';
['yu'] = 'y:';
['yun'] = 'y:n';
['yut'] = 'yt̚';
['m'] = 'm̩';
['ng'] = 'ŋ̩';
};
};
-- Jyutping
['jyutping'] = {
['label'] = '粵拼';
['link'] = '香港語言學學會粵語拼音方案';
['f'] = reconstruct_jyutping;
['initials'] = {
[''] = '';
['b'] = 'b';
['p'] = 'p';
['m'] = 'm';
['f'] = 'f';
['d'] = 'd';
['t'] = 't';
['n'] = 'n';
['l'] = 'l';
['g'] = 'g';
['k'] = 'k';
['ng'] = 'ng';
['h'] = 'h';
['gw'] = 'gw';
['kw'] = 'kw';
['w'] = 'w';
['z'] = 'z';
['c'] = 'c';
['s'] = 's';
['sh'] = 'sʲ'; -- non-standard notation added to handle actual speech
['sj'] = 'sʲ'; -- non-standard notation added to handle actual speech
['j'] = 'j';
};
['finals'] = {
['aa'] = 'aa';
['aai'] = 'aai';
['aau'] = 'aau';
['aam'] = 'aam';
['aan'] = 'aan';
['aang'] = 'aang';
['aap'] = 'aap';
['aat'] = 'aat';
['aak'] = 'aak';
['ai'] = 'ai';
['au'] = 'au';
['am'] = 'am';
['an'] = 'an';
['ang'] = 'ang';
['ap'] = 'ap';
['at'] = 'at';
['ak'] = 'ak';
['e'] = 'e';
['ei'] = 'ei';
['eng'] = 'eŋ';
['ek'] = 'ek';
['i'] = 'i';
['iu'] = 'iu';
['im'] = 'im';
['in'] = 'in';
['ing'] = 'ing';
['ip'] = 'ip';
['it'] = 'it';
['ik'] = 'ik';
['o'] = 'o';
['oi'] = 'oi';
['ou'] = 'ou';
['on'] = 'on';
['ong'] = 'ong';
['ot'] = 'ot';
['ok'] = 'ok';
['u'] = 'u';
['ui'] = 'ui';
['un'] = 'un';
['ung'] = 'ung';
['ut'] = 'ut';
['uk'] = 'uk';
['oe'] = 'oe';
['eoi'] = 'oei';
['eon'] = 'oen';
['oeng'] = 'oeŋ';
['eot'] = 'eot';
['oet'] = 'oet';
['oek'] = 'oek';
['yu'] = 'yu';
['yun'] = 'yun';
['yut'] = 'yut';
['m'] = 'm';
['ng'] = 'ng';
};
};
-- source: [[廣州話拼音方案]]
['pinyin_1960'] = {
['label'] = '廣州話拼音';
['link'] = '廣州話拼音方案';
['sublabel'] = '1960年版';
['f'] = reconstruct_pinyin_1960;
['initials'] = {
[''] = '';
['b'] = 'b';
['p'] = 'p';
['m'] = 'm';
['f'] = 'f';
['d'] = 'd';
['t'] = 't';
['n'] = 'n';
['l'] = 'l';
['g'] = 'g';
['k'] = 'k';
['ng'] = 'ng';
['h'] = 'h';
['gw'] = 'gu';
['kw'] = 'ku';
['w'] = 'w';
['z'] = 'z';
['c'] = 'c';
['s'] = 's';
['sh'] = 'sʰ'; -- non-standard notation added to handle actual speech
['sj'] = 'sʰ'; -- non-standard notation added to handle actual speech
['j'] = 'y';
};
['finals'] = {
['aa'] = 'a';
['aai'] = 'ai';
['aau'] = 'ao';
['aam'] = 'am';
['aan'] = 'an';
['aang'] = 'ang';
['aap'] = 'ab';
['aat'] = 'ad';
['aak'] = 'ag';
['ai'] = 'ei';
['au'] = 'ou';
['am'] = 'em';
['an'] = 'en';
['ang'] = 'eng';
['ap'] = 'eb';
['at'] = 'ed';
['ak'] = 'eg';
['e'] = 'é';
['ei'] = 'éi';
['eng'] = 'éng';
['ek'] = 'ég';
['i'] = 'i';
['iu'] = 'iu';
['im'] = 'im';
['in'] = 'in';
['ing'] = 'ing';
['ip'] = 'ib';
['it'] = 'id';
['ik'] = 'ig';
['o'] = 'o';
['oi'] = 'oi';
['ou'] = 'ô';
['on'] = 'on';
['ong'] = 'ông';
['ot'] = 'od';
['ok'] = 'og';
['u'] = 'u';
['ui'] = 'ui';
['un'] = 'un';
['ung'] = 'ong';
['ut'] = 'ud';
['uk'] = 'ug';
['oe'] = 'ê';
['eoi'] = 'êu';
['eon'] = 'ên';
['oeng'] = 'êng';
['eot'] = 'êd';
['oet'] = 'êd'; -- NOTE non-standard, clash
['oek'] = 'êg';
['yu'] = 'ü';
['yun'] = 'ün';
['yut'] = 'üd';
['m'] = 'm’'; -- XXX not supported
['ng'] = 'ng’'; -- XXX not supported
};
};
-- source: [[廣州話拼音方案]]
['pinyin_1980'] = {
['label'] = '廣州話拼音';
['link'] = '廣州話拼音方案';
['f'] = reconstruct_pinyin_1980;
['initials'] = {
[''] = '';
['b'] = 'b';
['p'] = 'p';
['m'] = 'm';
['f'] = 'f';
['d'] = 'd';
['t'] = 't';
['n'] = 'n';
['l'] = 'l';
['g'] = 'g';
['k'] = 'k';
['ng'] = 'ng';
['h'] = 'h';
['gw'] = 'gu';
['kw'] = 'ku';
['w'] = 'w';
['z'] = 'z';
['c'] = 'c';
['s'] = 's';
['sh'] = 'sʰ'; -- non-standard notation added to handle actual speech
['sj'] = 'sʰ'; -- non-standard notation added to handle actual speech
['j'] = 'y';
};
['finals'] = {
['aa'] = 'a';
['aai'] = 'ai';
['aau'] = 'ao';
['aam'] = 'am';
['aan'] = 'an';
['aang'] = 'ang';
['aap'] = 'ab';
['aat'] = 'ad';
['aak'] = 'ag';
['ai'] = 'ei';
['au'] = 'eo';
['am'] = 'em';
['an'] = 'en';
['ang'] = 'eng';
['ap'] = 'eb';
['at'] = 'ed';
['ak'] = 'eg';
['e'] = 'é';
['ei'] = 'éi';
['eng'] = 'éng';
['ek'] = 'ég';
['i'] = 'i';
['iu'] = 'iu';
['im'] = 'im';
['in'] = 'in';
['ing'] = 'ing';
['ip'] = 'ib';
['it'] = 'id';
['ik'] = 'ig';
['o'] = 'o';
['oi'] = 'oi';
['ou'] = 'ou';
['on'] = 'on';
['ong'] = 'ong';
['ot'] = 'od';
['ok'] = 'og';
['u'] = 'u';
['ui'] = 'ui';
['un'] = 'un';
['ung'] = 'ung';
['ut'] = 'ud';
['uk'] = 'ug';
['oe'] = 'ê';
['eoi'] = 'êu';
['eon'] = 'ên';
['oeng'] = 'êng';
['eot'] = 'êd';
['oet'] = 'êd'; -- NOTE non-standard, clash
['oek'] = 'êg';
['yu'] = 'ü';
['yun'] = 'ün';
['yut'] = 'üd';
['m'] = 'm';
['ng'] = 'ng';
};
};
-- source: [[教育學院拼音方案]]
['hkie'] = {
['label'] = '教育學院';
['link'] = '教育學院拼音方案';
['f'] = reconstruct_hkie;
['initials'] = {
[''] = '';
['b'] = 'b';
['p'] = 'p';
['m'] = 'm';
['f'] = 'f';
['d'] = 'd';
['t'] = 't';
['n'] = 'n';
['l'] = 'l';
['g'] = 'g';
['k'] = 'k';
['ng'] = 'ng';
['h'] = 'h';
['gw'] = 'gw';
['kw'] = 'kw';
['w'] = 'w';
['z'] = 'dz';
['c'] = 'ts';
['s'] = 's';
['sh'] = 'sʲ'; -- non-standard notation added to handle actual speech
['sj'] = 'sʲ'; -- non-standard notation added to handle actual speech
['j'] = 'j';
};
['finals'] = {
['aa'] = 'aa';
['aai'] = 'aai';
['aau'] = 'aau';
['aam'] = 'aam';
['aan'] = 'aan';
['aang'] = 'aang';
['aap'] = 'aap';
['aat'] = 'aat';
['aak'] = 'aak';
['ai'] = 'ai';
['au'] = 'au';
['am'] = 'am';
['an'] = 'an';
['ang'] = 'ang';
['ap'] = 'ap';
['at'] = 'at';
['ak'] = 'ak';
['e'] = 'e';
['ei'] = 'ei';
['eu'] = 'eu';
['eng'] = 'eng';
['ep'] = 'ep';
['et'] = 'et';
['ek'] = 'ek';
['i'] = 'i';
['iu'] = 'iu';
['im'] = 'im';
['in'] = 'in';
['ing'] = 'ing';
['ip'] = 'ip';
['it'] = 'it';
['ik'] = 'ik';
['o'] = 'o';
['oi'] = 'oi';
['ou'] = 'ou';
['on'] = 'on';
['ong'] = 'ong';
['ot'] = 'ot';
['ok'] = 'ok';
['u'] = 'u';
['ui'] = 'ui';
['un'] = 'un';
['ung'] = 'ung';
['ut'] = 'ut';
['uk'] = 'uk';
['oe'] = 'oe';
['eoi'] = 'oey';
['eon'] = 'oen';
['oeng'] = 'oeng';
['eot'] = 'oet';
['oet'] = 'oet'; -- NOTE non-standard, clash
['oek'] = 'oek';
['yu'] = 'y';
['yun'] = 'yn';
['yut'] = 'yt';
['m'] = 'm';
['ng'] = 'ng';
};
};
-- source: [[劉錫祥拼音]]
['sidneylau'] = {
['label'] = '劉錫祥';
['link'] = '劉錫祥拼音';
['f'] = reconstruct_sidneylau;
['initials'] = {
[''] = '';
['b'] = 'b';
['p'] = 'p';
['m'] = 'm';
['f'] = 'f';
['d'] = 'd';
['t'] = 't';
['n'] = 'n';
['l'] = 'l';
['g'] = 'g';
['k'] = 'k';
['ng'] = 'ng';
['h'] = 'h';
['gw'] = 'gw';
['kw'] = 'kw';
['w'] = 'w';
['z'] = 'j';
['c'] = 'ch';
['s'] = 's';
['sh'] = 'sʰ'; -- non-standard notation added to handle actual speech
['sj'] = 'sʰ'; -- non-standard notation added to handle actual speech
['j'] = 'y';
};
['finals'] = {
['aa'] = 'a';
['aai'] = 'aai';
['aau'] = 'aau';
['aam'] = 'aam';
['aan'] = 'aan';
['aang'] = 'aang';
['aap'] = 'aap';
['aat'] = 'aat';
['aak'] = 'aak';
['ai'] = 'ai';
['au'] = 'au';
['am'] = 'am';
['an'] = 'an';
['ang'] = 'ang';
['ap'] = 'ap';
['at'] = 'at';
['ak'] = 'ak';
['e'] = 'e';
['ei'] = 'ei';
['eng'] = 'eng';
['ek'] = 'ek';
['i'] = 'i';
['iu'] = 'iu';
['im'] = 'im';
['in'] = 'in';
['ing'] = 'ing';
['ip'] = 'ip';
['it'] = 'it';
['ik'] = 'ik';
['o'] = 'oh';
['oi'] = 'oi';
['ou'] = 'o';
['on'] = 'on';
['ong'] = 'ong';
['ot'] = 'ot';
['ok'] = 'ok';
['u'] = 'oo';
['ui'] = 'ooi';
['un'] = 'oon';
['ung'] = 'ung';
['ut'] = 'oot';
['uk'] = 'uk';
['oe'] = 'œ';
['eoi'] = 'ui';
['eon'] = 'un';
['oeng'] = 'eung';
['eot'] = 'ut';
['eot'] = 'eut'; -- NOTE non-standard
['oek'] = 'euk';
['yu'] = 'ue';
['yun'] = 'uen';
['yut'] = 'uet';
['m'] = 'm';
['ng'] = 'ng';
};
};
-- source: [[:en:Yale_romanization_of_Cantonese]]
['yale'] = {
['label'] = '耶魯';
['link'] = '耶魯粵語拼音';
['f'] = reconstruct_yale;
['initials'] = {
[''] = '';
['b'] = 'b';
['p'] = 'p';
['m'] = 'm';
['f'] = 'f';
['d'] = 'd';
['t'] = 't';
['n'] = 'n';
['l'] = 'l';
['g'] = 'g';
['k'] = 'k';
['ng'] = 'ng';
['h'] = 'h';
['gw'] = 'gw';
['kw'] = 'kw';
['w'] = 'w';
['z'] = 'j';
['c'] = 'ch';
['s'] = 's';
['sh'] = 'sʰ'; -- non-standard notation added to handle actual speech
['sj'] = 'sʰ'; -- non-standard notation added to handle actual speech
['j'] = 'y';
};
['finals'] = {
['aa'] = 'a';
['aai'] = 'aai';
['aau'] = 'aau';
['aam'] = 'aam';
['aan'] = 'aan';
['aang'] = 'aang';
['aap'] = 'aap';
['aat'] = 'aat';
['aak'] = 'aak';
['ai'] = 'ai';
['au'] = 'au';
['am'] = 'am';
['an'] = 'an';
['ang'] = 'ang';
['ap'] = 'ap';
['at'] = 'at';
['ak'] = 'ak';
['e'] = 'e';
['ei'] = 'ei';
['eng'] = 'eng';
['ek'] = 'ek';
['i'] = 'i';
['iu'] = 'iu';
['im'] = 'im';
['in'] = 'in';
['ing'] = 'ing';
['ip'] = 'ip';
['it'] = 'it';
['ik'] = 'ik';
['o'] = 'o';
['oi'] = 'oi';
['ou'] = 'ou';
['on'] = 'on';
['ong'] = 'ong';
['ot'] = 'ot';
['ok'] = 'ok';
['u'] = 'u';
['ui'] = 'ui';
['un'] = 'un';
['ung'] = 'ung';
['ut'] = 'ut';
['uk'] = 'uk';
['oe'] = 'eu';
['eoi'] = 'eui';
['eon'] = 'eun';
['oeng'] = 'eung';
['eot'] = 'eut';
['oet'] = 'eut'; -- NOTE non-standard, clash
['oek'] = 'euk';
['yu'] = 'yu';
['yun'] = 'yun';
['yut'] = 'yut';
['m'] = 'm';
['ng'] = 'ng';
};
};
-- source: [[粵語注音符號]]
['zhuyin_1931'] = {
['label'] = '注音';
['link'] = '粵語注音符號#民國政府時期';
['sublabel'] = '原型';
['f'] = reconstruct_zhuyin_1931;
['initials'] = {
[''] = '';
['b'] = 'ㄅ';
['p'] = 'ㄆ';
['m'] = 'ㄇ';
['f'] = 'ㄈ';
['d'] = 'ㄉ';
['t'] = 'ㄊ';
['n'] = 'ㄋ';
['l'] = 'ㄌ';
['g'] = 'ㄍ';
['k'] = 'ㄎ';
['ng'] = 'ㄫ';
['h'] = 'ㄏ';
['gw'] = '[[File:Bpmf-gw.svg|32px]]';
['kw'] = '[[File:Bpmf-kw.svg|32px]]';
['w'] = 'ㄨ';
['z'] = 'ㄐ';
['c'] = 'ㄑ';
['s'] = 'ㄒ';
--['sh'] = '???ʰ'; -- FIXME non-standard notation need to be added to handle actual speech
--['sj'] = '???ʰ'; -- FIXME non-standard notation need to be added to handle actual speech
['j'] = 'ㄧ';
};
['finals'] = {
['aa'] = 'ㄚ';
['aai'] = 'ㄞ';
['aau'] = 'ㄠ';
['aam'] = 'ㄚㄇ';
['aan'] = 'ㄢ';
['aang'] = 'ㄤ';
['aap'] = 'ㄚㄆ';
['aat'] = 'ㄚㄊ';
['aak'] = 'ㄚㄎ';
['ai'] = 'ㄟ';
['au'] = 'ㄡ';
['am'] = 'ㄜㄇ';
['an'] = 'ㄣ';
['ang'] = 'ㄥ';
['ap'] = 'ㄜㄆ';
['at'] = 'ㄜㄊ';
['ak'] = 'ㄜㄎ';
['e'] = 'ㄝ';
['ei'] = 'ㄝㄧ';
['eu'] = 'ㄝㄨ';
['em'] = 'ㄝㄇ';
['en'] = 'ㄝㄋ';
['eng'] = 'ㄝㄫ';
['ep'] = 'ㄝㄆ';
['et'] = 'ㄝㄊ';
['ek'] = 'ㄝㄎ';
['i'] = 'ㄧ';
['iu'] = 'ㄧㄨ';
['im'] = 'ㄧㄇ';
['in'] = 'ㄧㄋ';
['ing'] = 'ㄧㄫ';
['ip'] = 'ㄧㄆ';
['it'] = 'ㄧㄊ';
['ik'] = 'ㄧㄎ';
['o'] = 'ㄛ';
['oi'] = 'ㄛㄧ';
['ou'] = 'ㄛㄨ';
['on'] = 'ㄛㄋ';
['ong'] = 'ㄛㄫ';
['ot'] = 'ㄛㄊ';
['ok'] = 'ㄛㄎ';
['u'] = 'ㄨ';
['ui'] = 'ㄨㄧ';
['un'] = 'ㄨㄋ';
['ung'] = 'ㄨㄫ';
['ut'] = 'ㄨㄊ';
['uk'] = 'ㄨㄎ';
['oe'] = '[[File:Bpmf-oe.svg|32px]]';
['eoi'] = '[[File:Bpmf-oe.svg|32px]]ㄧ';
['eon'] = '[[File:Bpmf-oe.svg|32px]]ㄋ';
['oeng'] = '[[File:Bpmf-oe.svg|32px]]ㄫ';
['eot'] = '[[File:Bpmf-oe.svg|32px]]ㄊ';
['oet'] = '[[File:Bpmf-oe.svg|32px]]ㄊ'; -- NOTE non-standard, clash
['oek'] = '[[File:Bpmf-oe.svg|32px]]ㄎ';
['yu'] = 'ㄩ';
['yun'] = 'ㄩㄋ';
['yut'] = 'ㄩㄊ';
['m'] = 'ㄇ';
['ng'] = 'ㄫ';
};
};
-- source: [[粵語注音符號]]
['zhuyin_1932'] = {
['label'] = '注音';
['link'] = '粵語注音符號#民國政府時期';
['sublabel'] = '1932年版';
['f'] = reconstruct_zhuyin_1932;
['initials'] = {
[''] = '';
['b'] = 'ㄅ';
['p'] = 'ㄆ';
['m'] = 'ㄇ';
['f'] = 'ㄈ';
['d'] = 'ㄉ';
['t'] = 'ㄊ';
['n'] = 'ㄋ';
['l'] = 'ㄌ';
['g'] = 'ㄍ';
['k'] = 'ㄎ';
['ng'] = 'ㄫ';
['h'] = 'ㄏ';
['gw'] = 'ㄍㄨ';
['kw'] = 'ㄎㄨ';
['w'] = 'ㄨ';
['z'] = '[[File:Bpmf-zi.svg|32px]]';
['c'] = '[[File:Bpmf-ci.svg|32px]]';
['s'] = '[[File:Bpmf-si.svg|32px]]';
--['sh'] = '???ʰ'; -- FIXME non-standard notation need to be added to handle actual speech
--['sj'] = '???ʰ'; -- FIXME non-standard notation need to be added to handle actual speech
['j'] = 'ㄧ';
};
['finals'] = {
['aa'] = 'ㄚ';
['aai'] = 'ㄞ';
['aau'] = 'ㄠ';
['aam'] = '[[File:Bpmf-aam.svg|32px]]';
['aan'] = 'ㄢ';
['aang'] = 'ㄤ';
['aap'] = 'ㄚ<sub>ㄆ</sub>';
['aat'] = 'ㄚ<sub>ㄊ</sub>';
['aak'] = 'ㄚ<sub>ㄎ</sub>';
['ai'] = '[[File:Bpmf-aq.svg|32px]]ㄧ';
['au'] = '[[File:Bpmf-aq.svg|32px]]ㄨ';
['am'] = '[[File:Bpmf-aq.svg|32px]]ㆬ';
['an'] = '[[File:Bpmf-aq.svg|32px]]ㄣ';
['ang'] = '[[File:Bpmf-aq.svg|32px]]ㄥ';
['ap'] = '[[File:Bpmf-aq.svg|32px]]<sub>ㄆ</sub>';
['at'] = '[[File:Bpmf-aq.svg|32px]]<sub>ㄊ</sub>';
['ak'] = '[[File:Bpmf-aq.svg|32px]]<sub>ㄎ</sub>';
['e'] = 'ㄝ';
['ei'] = 'ㄟ';
['eu'] = 'ㄝㄨ';
['em'] = 'ㄝㆬ';
['en'] = 'ㄝㄣ';
['eng'] = 'ㄝㄥ';
['ep'] = 'ㄝ<sub>ㄆ</sub>';
['et'] = 'ㄝ<sub>ㄊ</sub>';
['ek'] = 'ㄝ<sub>ㄎ</sub>';
['i'] = 'ㄧ';
['iu'] = 'ㄧㄨ';
['im'] = 'ㄧㆬ';
['in'] = 'ㄧㄣ';
['ing'] = 'ㄧㄥ';
['ip'] = 'ㄧ<sub>ㄆ</sub>';
['it'] = 'ㄧ<sub>ㄊ</sub>';
['ik'] = 'ㄧ<sub>ㄎ</sub>';
['o'] = 'ㄛ';
['oi'] = 'ㄛㄧ';
['ou'] = 'ㄡ';
['on'] = '[[File:Bpmf-on.svg|32px]]';
['ong'] = '[[File:Bpmf-aong.svg|32px]]';
['ot'] = 'ㄛ<sub>ㄊ</sub>';
['ok'] = 'ㄛ<sub>ㄎ</sub>';
['u'] = 'ㄨ';
['ui'] = 'ㄨㄧ';
['un'] = 'ㄨㄣ';
['ung'] = 'ㄨㄥ';
['ut'] = 'ㄨ<sub>ㄊ</sub>';
['uk'] = 'ㄨ<sub>ㄎ</sub>';
['oe'] = '[[File:Bpmf-eu.svg|32px]]';
['eoi'] = '[[File:Bpmf-eu.svg|32px]]ㄧ';
['eon'] = '[[File:Bpmf-eu.svg|32px]]ㄣ';
['oeng'] = '[[File:Bpmf-eu.svg|32px]]ㄥ';
['eot'] = '[[File:Bpmf-eu.svg|32px]]<sub>ㄊ</sub>';
['oet'] = '[[File:Bpmf-eu.svg|32px]]<sub>ㄊ</sub>'; -- NOTE non-standard, clash
['oek'] = '[[File:Bpmf-eu.svg|32px]]<sub>ㄎ</sub>';
['yu'] = 'ㄩ';
['yun'] = 'ㄩㄣ';
['yut'] = 'ㄩ<sub>ㄊ</sub>';
['m'] = 'ㆬ';
['ng'] = 'ㆭ';
};
};
-- source: [[粵語注音符號]]
['zhuyin_1950'] = {
['label'] = '注音';
['link'] = '粵語注音符號#人民政府時期';
['sublabel'] = '1950年版';
['f'] = reconstruct_zhuyin_1950;
['initials'] = {
[''] = '';
['b'] = 'ㄅ';
['p'] = 'ㄆ';
['m'] = 'ㄇ';
['f'] = 'ㄈ';
['d'] = 'ㄉ';
['t'] = 'ㄊ';
['n'] = 'ㄋ';
['l'] = 'ㄌ';
['g'] = 'ㄍ';
['k'] = 'ㄎ';
['ng'] = 'ㄫ';
['h'] = 'ㄏ';
['gw'] = '[[File:Bpmf-gw.svg|32px]]';
['kw'] = '[[File:Bpmf-kw.svg|32px]]';
['w'] = 'ㄨ';
['z'] = 'ㄐ';
['c'] = 'ㄑ';
['s'] = 'ㄒ';
--['sh'] = '???ʰ'; -- FIXME non-standard notation need to be added to handle actual speech
--['sj'] = '???ʰ'; -- FIXME non-standard notation need to be added to handle actual speech
['j'] = 'ㄧ';
};
['finals'] = {
['aa'] = 'ㄚ';
['aai'] = 'ㄞ';
['aau'] = 'ㄠ';
['aam'] = 'ㄚ' .. dot; -- dot = U+323
['aan'] = 'ㄢ';
['aang'] = 'ㄤ';
['aap'] = 'ㄚ' .. dot;
['aat'] = 'ㄚ' .. dot;
['aak'] = 'ㄚ' .. dot;
['ai'] = 'ㄟ';
['au'] = 'ㄡ';
['am'] = '[[File:Bpmf-aq.svg|32px]]' .. dot;
['an'] = 'ㄣ';
['ang'] = 'ㄥ';
['ap'] = '[[File:Bpmf-aq.svg|32px]]' .. dot;
['at'] = '[[File:Bpmf-aq.svg|32px]]' .. dot;
['ak'] = '[[File:Bpmf-aq.svg|32px]]' .. dot;
['e'] = 'ㄝ';
['ei'] = 'ㄝㄧ';
['eu'] = 'ㄝㄨ';
['em'] = 'ㄝ' .. dot;
['en'] = 'ㄝ' .. dot;
['eng'] = 'ㄝ' .. dot;
['ep'] = 'ㄝ' .. dot;
['et'] = 'ㄝ' .. dot;
['ek'] = 'ㄝ' .. dot;
['i'] = 'ㄧ';
['iu'] = 'ㄧㄨ';
['im'] = 'ㄧ' .. dot;
['in'] = 'ㄧ' .. dot;
['ing'] = 'ㄧ' .. dot;
['ip'] = 'ㄧ' .. dot;
['it'] = 'ㄧ' .. dot;
['ik'] = 'ㄧ' .. dot;
['o'] = 'ㄛ';
['oi'] = 'ㄛㄧ';
['ou'] = 'ㄛㄨ';
['on'] = 'ㄛ' .. dot;
['ong'] = 'ㄛ' .. dot;
['ot'] = 'ㄛ' .. dot;
['ok'] = 'ㄛ' .. dot;
['u'] = 'ㄨ';
['ui'] = 'ㄨㄧ';
['un'] = 'ㄨ' .. dot;
['ung'] = 'ㄨ' .. dot;
['ut'] = 'ㄨ' .. dot;
['uk'] = 'ㄨ' .. dot;
['oe'] = '[[File:Bpmf-oe.svg|32px]]';
['eoi'] = '[[File:Bpmf-oe.svg|32px]]ㄧ';
['eon'] = '[[File:Bpmf-oe.svg|32px]]' .. dot;
['oeng'] = '[[File:Bpmf-oe.svg|32px]]' .. dot;
['eot'] = '[[File:Bpmf-oe.svg|32px]]' .. dot;
['oet'] = '[[File:Bpmf-oe.svg|32px]]' .. dot; -- NOTE non-standard, clash
['oek'] = '[[File:Bpmf-oe.svg|32px]]' .. dot;
['yu'] = 'ㄩ';
['yun'] = 'ㄩ' .. dot;
['yut'] = 'ㄩ' .. dot;
['m'] = 'ㄇ';
['ng'] = 'ㄫ';
};
};
-- source: [[粵語點字]]
['braille'] = {
['label'] = '點字';
['link'] = '粵語點字';
['f'] = reconstruct_braille;
['initials'] = {
[''] = '';
['b'] = '⠏';
['p'] = '⠯';
['m'] = '⠍';
['f'] = '⠋';
['d'] = '⠞';
['t'] = '⠾';
['n'] = '⠝';
['l'] = '⠇';
['g'] = '⠅';
['k'] = '⠗';
['ng'] = '⠛';
['h'] = '⠓';
['gw'] = '⠟';
['kw'] = '⠻';
['w'] = '⠺';
['z'] = '⠉';
['c'] = '⠭';
['s'] = '⠎';
--['sh'] = '???ʰ'; -- FIXME non-standard notation need to be added to handle actual speech
['j'] = '⠚';
};
['finals'] = {
['aa'] = '⠃';
['aai'] = '⠬';
['aau'] = '⠌';
['aam'] = '⠜';
['aan'] = '⠘';
['aang'] = '⠉';
['aap'] = '⠏';
['aat'] = '⠞';
['aak'] = '⠅';
['ai'] = '⠩';
['au'] = '⠡';
['am'] = '⠸';
['an'] = '⠫';
['ang'] = '⠛';
['ap'] = '⠢';
['at'] = '⠔';
['ak'] = '⠨';
['e'] = '⠑';
['ei'] = '⠓';
['eng'] = '⠶';
['ek'] = '⠺';
['i'] = '⠊';
['iu'] = '⠽';
['im'] = '⠖';
['in'] = '⠲';
['ing'] = '⠴';
['ip'] = '⠯';
['it'] = '⠾';
['ik'] = '⠗';
['o'] = '⠕';
['oi'] = '⠣';
['ou'] = '⠧';
['on'] = '⠝';
['ong'] = '⠰';
['ot'] = '⠋';
['ok'] = '⠻';
['u'] = '⠥';
['ui'] = '⠳';
['un'] = '⠮';
['ung'] = '⠦';
['ut'] = '⠵';
['uk'] = '⠟';
['oe'] = '⠱';
['eoi'] = '⠚';
['eon'] = '⠎';
['oeng'] = '⠒';
['eot'] = '⠭';
['oet'] = '⠭'; -- XXX non-standard, clash; not described in article, guessing
['oek'] = '⠪';
['yu'] = '⠹';
['yun'] = '⠆';
['yut'] = '⠷';
['m'] = '⠍'; -- XXX not described in article, guessing
['ng'] = '⠛'; -- XXX not described in article, guessing
};
};
};
local function yalify_syllable (s, id)
local it;
if id == nil then
id = default_scheme;
end
local mapping = mappings[id];
local initials = mapping.initials;
local finals = mapping.finals;
local f = mapping.f;
if s then
local all_caps_p = s == mw.ustring.upper(s);
local capped_p = s == (mw.ustring.upper(mw.ustring.sub(s, 1, 1))
.. mw.ustring.lower(mw.ustring.sub(s, 2)));
local pat_part1_syllabic_m = '^()(m)';
local pat_part1_syllabic_ng = '^()(ng)';
local pat_part1 = '^([bcdfghjklmnpstwz]*)([a-z]+)';
local pat_tone0 = '([123456789¹²³⁴⁵⁶⁷⁸⁹₁₂₃₄₅₆₇₈₉])[%*%-]';
local pat_tone = '([123456789¹²³⁴⁵⁶⁷⁸⁹₁₂₃₄₅₆₇₈₉])';
local pat_part2 = '([^%a]-)$';
local initial, final, tone0, tone, punctuation;
s = mw.ustring.lower(s);
-- syllabic m?
if not tone then
initial, final, tone0, tone, punctuation = mw.ustring.match(s, pat_part1_syllabic_m .. pat_tone0 .. pat_tone .. pat_part2);
if not tone then
initial, final, tone, punctuation = mw.ustring.match(s, pat_part1_syllabic_m .. pat_tone .. pat_part2);
end
initial = '';
end
-- syllabic ng?
if not tone then
initial, final, tone0, tone, punctuation = mw.ustring.match(s, pat_part1_syllabic_ng .. pat_tone0 .. pat_tone .. pat_part2);
if not tone then
initial, final, tone, punctuation = mw.ustring.match(s, pat_part1_syllabic_ng .. pat_tone .. pat_part2);
end
initial = '';
end
-- normal syllables?
if not tone then
initial, final, tone0, tone, punctuation = mw.ustring.match(s, pat_part1 .. pat_tone0 .. pat_tone .. pat_part2);
if not tone then
initial, final, tone, punctuation = mw.ustring.match(s, pat_part1 .. pat_tone .. pat_part2);
end
end
-- figure out what the actual tone(s) is (are) and convert into an "object"
-- tone value in usual 6-tone system is tone.actual.senary
if tone then
tone = tonumber(mw.ustring.toNFKC(tone)); -- remove superscripting and subscripting, then convert to number
if tone0 then
tone0 = tonumber(mw.ustring.toNFKC(tone0));
end
local novenary_tone = tone;
local novenary_tone0 = tone0;
if final:match('[ptk]$') then
if tone == 1 then
novenary_tone = 7;
elseif tone == 3 then
novenary_tone = 8;
elseif tone == 6 then
novenary_tone = 9;
elseif tone == 7 then
tone = 1;
elseif tone == 8 then
tone = 3;
elseif tone == 9 then
tone = 6;
end
if tone0 then
if tone0 == 1 then
novenary_tone0 = 7;
elseif tone0 == 3 then
novenary_tone0 = 8;
elseif tone0 == 6 then
novenary_tone0 = 9;
elseif tone0 == 7 then
tone0 = 1;
elseif tone0 == 8 then
tone0 = 3;
elseif tone0 == 9 then
tone0 = 6;
end
end
end
tone = {
['actual'] = {
['senary'] = tone;
['quaternary'] = ((novenary_tone - 1) % 3 + 1) * (1 - math.floor((novenary_tone - 1)/6)) + math.floor((novenary_tone - 1)/6) * 4;
['novenary'] = novenary_tone;
['feminine_p'] = tone < 4;
['masculine_p'] = tone > 3;
};
};
if tone0 then
tone.canonical = {
['senary'] = tone0;
['quaternary'] = ((novenary_tone0 - 1) % 3 + 1) * (1 - math.floor((novenary_tone0 - 1)/6)) + math.floor((novenary_tone0 - 1)/6) * 4;
['novenary'] = novenary_tone0;
['feminine_p'] = tone0 < 4;
['masculine_p'] = tone0 > 3;
};
end
end
if initial then
if initials[initial] then
initial = initials[initial];
end
if finals[final] then
final = finals[final];
end
end
if tone then
it = f(initial, final, tone, punctuation, capped_p, all_caps_p);
elseif not mapping.ignore_spaces_p or mw.ustring.match(s, '%S') then
it = s;
else
it = '';
end
--it = p.cvs({initial = initial, final = final, tone = tone});--XXXZZZ
end
if it then
it = it:gsub('(%[%[File:[^%[%]]+%]%])', '<span class=img-as-char>%1</span>');
end
return it;
end
local function yalify (segments, id)
local it = '';
if not id then
id = 'yale';
end
local mapping = mappings[id];
if mapping.prefix then
it = it .. mapping.prefix;
end
for _, s in pairs(segments) do
it = it .. yalify_syllable(s, id);
end
if mapping.suffix then
it = it .. mapping.suffix;
end
return it;
end
local function break_into_segments (s) -- I hate Lua
local it = {};
local pat_part1 = '[%a]+[1-9¹²³⁴⁵⁶⁷⁸⁹₁₂₃₄₅₆₇₈₉]';
local pat_part2 = '%*[1-9¹²³⁴⁵⁶⁷⁸⁹₁₂₃₄₅₆₇₈₉]';
local pat1 = '^(' .. pat_part1 .. ')';
local pat2 = '^(' .. pat_part1 .. pat_part2 .. ')';
while s and #s > 0 do
local pre = '';
while s and #s > 0 and not mw.ustring.match(s, pat1) do
pre = pre .. mw.ustring.sub(s, 1, 1);
s = mw.ustring.sub(s, 2);
end
if #pre > 0 then
table.insert(it, pre);
end
local m, post = mw.ustring.match(s, pat2 .. '(.*)$');
if m then
table.insert(it, m);
else
m, post = mw.ustring.match(s, pat1 .. '(.*)$');
if m then
table.insert(it, m);
end
end
s = post;
end
return it;
end
local function blacklisted_p (s)
local it = false;
for _, det in pairs(break_into_segments(s)) do
for i, pat in pairs(jyutping_blacklist) do
if mw.ustring.match(det, pat) then
it = true;
end
if it then break end;
end
if it then break end;
end
return it;
end
local function make_transcription( scheme, s, ruby_mode_p, ruby )
local it = '';
local annotation;
if ruby_mode_p then
for i = 1, #ruby do
local entity = ruby[i];
if entity.rt then
if scheme == 'jyutping' then
annotation = ' title="對應 IPA：' .. remove_tags(yalify(break_into_segments(entity.rt), 'ipa_phonemic')) .. '"';
else
annotation = ' title="對應粵拼：' .. remove_tags(entity.rt) .. '"';
end
it = it .. '<ruby><rb>' .. entity.rb .. '</rb><rp> (</rp><rt>';
it = it .. '<span class=transl-yue-ruby data-type=' .. scheme .. annotation .. '>';
it = it .. yalify(break_into_segments(entity.rt), scheme);
it = it .. '</span>';
it = it .. '</rt><rp>) </rp></ruby>';
else
it = it .. entity.rb;
end
end
else
if scheme == 'jyutping' then
annotation = ' title="對應 IPA：' .. remove_tags(yalify(break_into_segments(s), 'ipa_phonemic')) .. '"';
else
annotation = ' title="對應粵拼：' .. remove_tags(s) .. '"';
end
it = it .. '<span class=transl-yue data-type=' .. scheme .. annotation .. '>';
it = it .. yalify(break_into_segments(s), scheme);
it = it .. '</span>';
end
return it;
end
-- Entry point
p.ruby = function( frame )
return p.yalify(frame, true);
end
-- Entry point
p.yalify = function (frame, ruby_mode_p)
local parent = frame:getParent();
local s;
local scheme = nil;
local variant;
local label_p;
local ruby, rt_mode_p;
local vernacular, literary;
local borrowed, approximation;
for _, a in pairs({frame, parent}) do
if a then
for k, v in pairs(a.args) do
v = v:gsub('^%s+', ''):gsub('%s+$', '');
if type(k) == 'number' then
if ruby_mode_p then
if not ruby then
ruby = {};
end
if rt_mode_p then
if #v > 0 then
ruby[#ruby].rt = v;
end
rt_mode_p = false;
else
table.insert(ruby, { ['rb'] = v; });
rt_mode_p = true;
end
else
if s then
s = s .. ' ' .. v;
else
s = v;
end
end
elseif k == 'type' or k == '方案' then
scheme = v;
elseif k == 'variant' or k == '版本' then
variant = v;
elseif k == 'label' or k == '標題' then
label_p = interpret_boolean(v);
elseif k == 'vernacular' or k == 'colloquial' or k == '白' then
vernacular = v;
elseif k == 'literary' or k == 'formal' or k == '文' then
literary = v;
elseif k == 'borrowed' or k == '粵化' or k == '借' then
borrowed = v;
elseif k == 'approx' or k == '類似' or k == '類' or k == '似' then
approximation = v;
else
error('不明參數 ｢' .. k .. '｣');
end
end
end
end
if not scheme then
for _, det in pairs({s, vernacular, literary, borrowed, approximation}) do
if det and blacklisted_p(det) then
scheme = fallback_scheme;
end
if scheme then break end;
end
if not scheme then
scheme = default_scheme;
end
end
if scheme and not schemes[scheme] then
if schemes[mw.ustring.lower(scheme)] then
scheme = mw.ustring.lower(scheme);
else
error('唔知 ｢' .. scheme .. '｣ 係乜方案');
end
end
if scheme and variant then
if not (variants[schemes[scheme]] and variants[schemes[scheme]][variant]) then
error('｢' .. scheme .. '｣ 方案冇版本叫 ｢' .. variant .. '｣');
end
variant = variants[schemes[scheme]][variant];
elseif scheme and default_variants[schemes[scheme]] then
variant = default_variants[schemes[scheme]];
end
if scheme then
scheme = schemes[scheme];
if variant then
scheme = scheme .. '_' .. variant;
end
if not mappings[scheme] then
error('Internal error: ' .. scheme .. ': No such scheme in mappings table');
end
end
if borrowed and (s or vernacular or literary) then
error('唔可以同時指定粵化讀音同實際嘅粵文讀音');
elseif approximation and (s or vernacular or literary) then
error('唔可以同時指定類似粵讀同實際嘅粵文讀音');
end
local it = '';
if label_p and approximation then
it = it .. '類似';
end
if label_p and mappings[scheme].label then
local prefix, suffix;
if mappings[scheme].link then
prefix = '[[' .. mappings[scheme].link .. '|';
suffix = ']]';
end
it = it .. prefix .. mappings[scheme].label .. suffix;
if mappings[scheme].sublabel then
it = it .. '<sup>' .. mappings[scheme].sublabel .. '</sup>';
end
it = it .. '：';
end
if ruby_mode_p and (vernacular or literary) then
error('注音模式唔可以分文白異讀');
elseif ruby_mode_p and borrowed then
error('注音模式唔可以指定係借詞');
elseif ruby_mode_p and approximation then
error('注音模式唔可以指定係類似讀音');
elseif ruby_mode_p then
it = it .. make_transcription(scheme, s, ruby_mode_p, ruby);
elseif borrowed and approximation then
it = it .. make_transcription(scheme, approximation, ruby_mode_p, ruby);
it = it .. '，<small>[[借詞|粵化口語音]]：</small>';
it = it .. make_transcription(scheme, borrowed, ruby_mode_p, ruby);
elseif borrowed then
it = it .. '<small>[[借詞|粵化口語音]]：</small>';
it = it .. make_transcription(scheme, borrowed, ruby_mode_p, ruby);
elseif approximation then
it = it .. make_transcription(scheme, approximation, ruby_mode_p, ruby);
elseif s and literary and (not vernacular or s == vernacular) then
it = it .. make_transcription(scheme, s, ruby_mode_p, ruby);
it = it .. '，<small>[[文白異讀|文讀]]：</small>';
it = it .. make_transcription(scheme, literary, ruby_mode_p, ruby);
elseif s and vernacular and (not literary or s == literary) then
it = it .. make_transcription(scheme, s, ruby_mode_p, ruby);
it = it .. '，<small>[[文白異讀|白讀]]：</small>';
it = it .. make_transcription(scheme, vernacular, ruby_mode_p, ruby);
elseif literary and vernacular then
it = it .. '<small>[[文白異讀|白讀]]：</small>';
it = it .. make_transcription(scheme, vernacular, ruby_mode_p, ruby);
it = it .. '，<small>[[文白異讀|文讀]]：</small>';
it = it .. make_transcription(scheme, literary, ruby_mode_p, ruby);
elseif s and vernacular and literary then
error('標咗三種讀音，要鏟走其中一種');
elseif s then
it = it .. make_transcription(scheme, s, ruby_mode_p, ruby);
else
error('冇指定讀音');
end
-- request our style sheet
it = table.concat ({ frame:extensionTag('templatestyles', '', {src=styles}), it });
return it;
end
local function td_note (mapping, cond_p)
local it = '';
if mapping.label and cond_p then
it = it .. '|' .. mapping.label;
if mapping.sublabel then
it = it .. '，' .. mapping.sublabel;
end
it = it .. '\n';
else
it = it .. '|\n';
end
return it;
end
local function td_seealso (mapping, cond_p)
local it = '';
if mapping.link and cond_p then
it = it .. '|[[' .. mapping.link .. ']]\n';
else
it = it .. '|\n';
end
return it;
end
p.dump_schemes = function (frame)
local known_schemes = {};
local scheme_params = {};
local broken = '冇定義，純粹楔位';
local unk = 'style="background:#ececec;color:#2C2C2C;font-size:smaller;text-align:center" class=table-na'; -- copied from Template:Unk
local q = require('模組:漢字/sort');
for k, v in pairs(schemes) do -- invert the schemes table and keep an array that can be sorted
if known_schemes[v] then
table.insert(known_schemes[v], k);
else
known_schemes[v] = { k };
end
table.insert(scheme_params, k);
end
table.sort(scheme_params, q.by_stroke_count);
local it = '';
it = it .. '{|class="sortable wikitable"\n';
it = it .. '!colspan=3|方案\n';
it = it .. '!colspan=5|版本\n';
it = it .. '|-\n';
it = it .. '!參數\n';
it = it .. '!識別\n';
it = it .. '!預設版本\n';
it = it .. '!參數\n';
it = it .. '!識別\n';
it = it .. '!總識別\n';
it = it .. '!註\n';
it = it .. '!睇埋\n';
it = it .. '|-\n';
for i = 1, #scheme_params do
local scheme_param = scheme_params[i];
local scheme_id = schemes[scheme_param];
local known_variants = {};
local variant_params = {};
if variants[scheme_id] then
for k, v in pairs(variants[scheme_id]) do -- invert the variants table
if known_variants[v] then
table.insert(known_variants[v], k);
else
known_variants[v] = { k };
end
table.insert(variant_params, k);
end
end
table.sort(variant_params, q.by_stroke_count);
local td = '|';
if #variant_params > 1 and scheme_param == scheme_id then
td = td .. 'rowspan=' .. #variant_params .. '|';
end
if scheme_param == scheme_id then
it = it .. td_insert_attr(td_insert_attr(td, 'colspan=2 align=center'),
'data-sort-value=' .. q.data_sort_value(scheme_param))
.. "'''" .. scheme_param .. "'''\n";
else
it = it .. td_insert_attr(td, 'data-sort-value=' .. q.data_sort_value(scheme_param))
.. scheme_param .. '\n';
it = it .. td .. scheme_id .. '\n';
end
if default_variants[scheme_id] then
it = it .. td .. default_variants[scheme_id] .. '\n';
else
it = it .. td_insert_attr(td, unk) .. '唔適用\n';
end
if scheme_param ~= scheme_id then
if mappings[scheme_id] then
-- to determine whether scheme_id refers to a scheme or a variant,
-- repeat the scheme_param ~= scheme_id test with scheme_id as
-- "scheme_param", we'll get our "scheme_id" from the schemes table
-- just as we did at the beginning of the outer loop
local det = schemes[scheme_id];
if scheme_id ~= det then
it = it .. '|colspan=5|請睇總識別碼 ｢' .. scheme_id .. '｣\n';
else
it = it .. '|colspan=5|請睇方案 ｢' .. scheme_id .. '｣\n';
end
else
it = it .. '|colspan=5|請睇方案 ｢' .. scheme_id .. '｣\n';
end
it = it .. '|-\n';
elseif #variant_params == 0 then
it = it .. '|colspan=2 ' .. unk .. '|唔適用\n';
it = it .. '|' .. scheme_id .. '\n';
if mappings[scheme_id] then
it = it .. td_note(mappings[scheme_id], true);
it = it .. td_seealso(mappings[scheme_id], true);
else
it = it .. '|colspan=2|' .. broken .. '\n';
end
it = it .. '|-\n';
else
for j = 1, #variant_params do
local variant_name = variant_params[j];
local variant_id = variants[scheme_id][variant_name];
local id = scheme_id .. '_' .. variant_id;
local mod1 = '';
if variant_name == variant_id then
if known_schemes[id] then
mod1 = "'''";
end
it = it .. "|colspan=2 align=center data-sort-value="
.. q.data_sort_value(variant_name) .. "|'''" .. variant_name .. "'''\n";
else
it = it .. '|data-sort-value=' .. q.data_sort_value(variant_name) .. '|'
.. variant_name .. '\n';
it = it .. '|' .. variant_id .. '\n';
end
it = it .. '|' .. mod1 .. id .. mod1 .. '\n';
if mappings[id] then
it = it .. td_note(mappings[id], variant_name == variant_id);
it = it .. td_seealso(mappings[id], variant_name == variant_id);
else
it = it .. '|colspan=2 align=center|' .. broken .. '\n';
end
it = it .. '|-\n';
end
end
end
it = it .. '|}\n';
-- request our style sheet
it = table.concat ({ frame:extensionTag('templatestyles', '', {src=styles}), "\n", it });
return it;
end
p.test = function ()
assert(blacklisted_p('shep1 pat4'));
assert(not blacklisted_p('sep1 pat4'));
end
return p;